Legal claims defining the scope of protection, as filed with the USPTO.
2. The colorization apparatus according to claim 1, wherein the resultant layer of the automatic colorization includes a portion that has been colorized and a portion that has not been colorized.
4. The colorization apparatus according to claim 3, wherein the hint information is information that provides correspondence between a color selected by the user and a portion that is designated by the user as a portion to be colorized with the selected color, with respect to the first layer selected by the user.
5. The colorization apparatus according to claim 4, wherein the user interface establishes the correspondence by allowing the user to place a dot on the portion to be colorized with the selected color.
7. The colorization apparatus according to claim 1, wherein the managed plurality of layers include a background layer, and the first layer selected by the user is a layer superimposed on the background layer.
8. The colorization apparatus according to claim 7, wherein the layer superimposed on the background layer is a layer of a person.
9. The colorization apparatus according to claim 1, wherein the at least one processor is configured to perform another automatic colorization with respect to the second layer in addition to the first layer selected by the user.
10. The colorization apparatus according to claim 9, wherein the at least one processor is configured to synthesize at least resultant layers of the automatic colorization and the second layer of the another automatic colorization into the synthesized colored image.
11. The colorization apparatus according to claim 1, wherein the at least one processor is configured to perform the automatic colorization based on a colorization model.
12. The colorization apparatus according to claim 11, wherein the colorization model includes a neural network.
13. The coloring apparatus according to claim 1, wherein the at least one processor is configured to receive a color and a position for target image data of the first layer selected by the user, the color and the position for the target image data being selected by the user as a hint for the automatic colorization of the target image data.
18. The method according to claim 17, wherein the establishing comprises establishing the correspondence by placing, through the displayed user interface, a dot on the portion that is to be colorized with the selected color.
20. The method according to claim 15, wherein the automatic colorization is executed based on a colorization model including a neural network.
22. The non-transitory computer readable medium according to claim 21, wherein the editing software is further configured to cause the at least one processor to execute the automatic colorization with respect to the identified at least one layer.
23. The non-transitory computer readable medium according to claim 21, wherein the editing software is further configured to cause the at least one processor to synthesize at least (i) the resultant layer of the automatic colorization and (ii) the another layer that is not subject to the automatic colorization, into the image to be displayed on the display device.
24. The non-transitory computer readable medium according to claim 21, wherein the resultant layer of the automatic colorization includes a portion that has been colorized and a portion that has not been colorized.
26. The non-transitory computer readable medium according to claim 25, wherein the hint information is information that provides correspondence between a color selected by the user and a portion that is designated by the user as a portion to be colorized with the selected color, with respect to the identified at least one layer.
27. The non-transitory computer readable medium according to claim 26, wherein the user interface establishes the correspondence by allowing the user to place a dot on the portion that is to be colorized with the selected color.
28. The non-transitory computer readable medium according to claim 21, wherein the editing software is further configured to cause the at least one processor to provide an editing function of editing a result of executing the automatic colorization.
29. The non-transitory computer readable medium according to claim 21, wherein the identified at least one layer is a managed layer that has an image that has been generated or pasted using the editing software.
30. The non-transitory computer readable medium according to claim 21, wherein the at least one processor is configured to execute the automatic colorization based on a trained neural network that has been trained to perform colorization processing on image data.
32. The apparatus according to claim 31, wherein the at least one processor is further configured to execute the automatic colorization with respect to the identified at least one layer.
33. The apparatus according to claim 31, wherein the at least one processor is further configured to synthesize at least (i) the resultant layer of the automatic colorization and (ii) the another layer that is not subject to the automatic colorization, into the image to be displayed on the display device.
34. The apparatus according to claim 31, wherein the resultant layer of the automatic colorization includes a portion that has been colorized and a portion that has not been colorized.
36. The apparatus according to claim 35, wherein the hint information is information that provides correspondence between a color selected by the user and a portion that is designated by the user as a portion to be colorized with the selected color, with respect to the identified at least one layer.
37. The apparatus according to claim 36, wherein the user interface establishes the correspondence by allowing the user to place a dot on the portion that is to be colorized with the selected color.
38. The apparatus according to claim 31, wherein the at least one processor is configured to provide an image editing function of editing a result of executing the automatic colorization.
39. The apparatus according to claim 31, wherein the identified at least one layer is a managed layer that has an image that has been generated or pasted using an image editing function provided by the at least one processor.
40. The apparatus according to claim 31, wherein the at least one processor is configured to execute the automatic colorization based on a trained neural network that has been trained to perform colorization processing on image data.
42. The method according to claim 41, wherein the resultant layer of the automatic colorization includes a portion that has been colorized and a portion that has not been colorized.
44. The method according to claim 43, wherein the hint information is information that provides correspondence between a color selected by the user and a portion that is designated by the user as a portion to be colorized with the selected color, with respect to the first layer selected by the user.
47. The method according to claim 41, wherein the managed plurality of layers include a background layer, and the first layer selected by the user is a layer superimposed on the background layer.
48. The method according to claim 47, wherein the layer superimposed on the background layer is a layer of a person.
52. The method according to claim 51, wherein the colorization model includes a neural network.
55. The non-transitory computer readable medium according to claim 54, wherein the resultant layer of the automatic colorization includes a portion that has been colorized and a portion that has not been colorized.
57. The non-transitory computer readable medium according to claim 56, wherein the hint information is information that provides correspondence between a color selected by the user and a portion that is designated by the user as a portion to be colorized with the selected color, with respect to the first layer selected by the user.
60. The non-transitory computer readable medium according to claim 54, wherein the managed plurality of layers include a background layer, and the first layer selected by the user is a layer superimposed on the background layer.
61. The non-transitory computer readable medium according to claim 60, wherein the layer superimposed on the background layer is a layer of a person.
65. The non-transitory computer readable medium according to claim 54, wherein the colorization model includes a neural network.
Unknown
February 27, 2024
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.